Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "any"

    oai_token-act-pair · gpt-3.5-turbo

    the word "any."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isable
    -0.65
    pires
    -0.64
     reprodu
    -0.63
     brim
    -0.61
     authenticity
    -0.59
     gou
    -0.59
     repl
    -0.59
     commun
    -0.59
     fung
    -0.59
    reditary
    -0.58
    POSITIVE LOGITS
    where
    1.06
    THING
    0.98
    body
    0.87
    emi
    0.81
    ika
    0.79
    one
    0.79
    agh
    0.75
    Õ
    0.75
    uan
    0.75
    ahu
    0.74
    Act Density 0.015%

    No Known Activations